What are the hardware requirements for Qwen3.5 122B A10B SFT?

Qwen3.5 122B A10B SFT requires approximately 11.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Qwen3.5 122B A10B SFT and how large is it?

Qwen3.5 122B A10B SFT is developed by Zhongzhi1228, a model with 122b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Qwen3.5 122B A10B SFT?

Qwen3.5 122B A10B SFT is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Qwen3.5 122B A10B SFT by Zhongzhi1228 — VRAM 11.6GB

Name: Qwen3.5 122B A10B SFT
Author: Zhongzhi1228

Qwen3.5 122B A10B SFT is an open-source language model by Zhongzhi1228. Features: 122b LLM, VRAM: 11.6GB, License: cc-by-4.0.

Base model:finetune:qwen/qwen3... Base model:qwen/qwen3.5-122b-a... Conversational Endpoints compatible Image-text-to-text Qwen3 5 Qwen3 5 moe Recursive-task-synthesis Region:us Safetensors Sharded Supervised-fine-tuning Tensorflow Terminal-agents

Model Card on HF 🤗: https://huggingface.co/Zhongzhi1228/Qwen3.5-122B-A10B-SFT

Qwen3.5 122B A10B SFT Parameters and Internals

LLM Name	Qwen3.5 122B A10B SFT
Repository 🤗	https://huggingface.co/Zhongzhi1228/Qwen3.5-122B-A10B-SFT
Base Model(s)	Qwen/Qwen3.5-122B-A10B Qwen/Qwen3.5-122B-A10B
Model Size	122b
Required VRAM	11.6 GB
Updated	2026-08-09
Maintainer	Zhongzhi1228
Model Type	qwen3_5_moe
Model Files	1.6 GB: 1-of-145 0.0 GB: 2-of-145 0.1 GB: 3-of-145 0.2 GB: 4-of-145 0.1 GB: 5-of-145 0.6 GB: 6-of-145 0.3 GB: 7-of-145 0.4 GB: 8-of-145 0.4 GB: 9-of-145 0.1 GB: 10-of-145 0.1 GB: 11-of-145 0.2 GB: 12-of-145 0.0 GB: 13-of-145 0.0 GB: 14-of-145 0.4 GB: 15-of-145 0.2 GB: 16-of-145 0.1 GB: 17-of-145 0.2 GB: 18-of-145 0.2 GB: 19-of-145 0.4 GB: 20-of-145 0.1 GB: 21-of-145 0.2 GB: 22-of-145 0.2 GB: 23-of-145 0.1 GB: 24-of-145 0.2 GB: 25-of-145 0.1 GB: 26-of-145 0.3 GB: 27-of-145 0.4 GB: 28-of-145 0.1 GB: 29-of-145 0.0 GB: 30-of-145 0.1 GB: 31-of-145 0.5 GB: 32-of-145 0.4 GB: 33-of-145 0.2 GB: 34-of-145 0.2 GB: 35-of-145 1.6 GB: 36-of-145 0.3 GB: 37-of-145 0.1 GB: 38-of-145 0.4 GB: 39-of-145 0.3 GB: 40-of-145 0.1 GB: 41-of-145 0.1 GB: 42-of-145
Model Architecture	Qwen3_5MoeForConditionalGeneration
License	cc-by-4.0
Transformers Version	4.57.0.dev0

Rank the Qwen3.5 122B A10B SFT capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Qwen3.5 122B A10B SFT

Best Alternatives	Context / RAM	Downloads	Likes
Qwen3.5 122B A10B NVFP4	0K / 83.5 GB	248732	49
Qwen3.5 122B A10B Abliterated	0K / 248.6 GB	49	5
...en3.5 122B A10B Int4 AutoRound	0K / 72 GB	142311	45
Qwen3.5 122B A10B OQ4 Mtp	0K / 72.5 GB	925	3
Qwen3.5 122B A10B Bf16	0K / 224.2 GB	2773	2
Qwen3.5 REAP 97B A10B	0K / 194.2 GB	31	17
Qwen3.5 122B A10B WMix48	0K / 73.2 GB	215	3
Qwen3.5 122B A10B WMix58	0K / 87.5 GB	214	3
Qwen3.5 122B A10B WMix68	0K / 102.1 GB	156	1
Qwen3.5 122B A10B FP8	0K / 126.3 GB	1271983	112

Note: green Score (e.g. "73.2") means that the model is better than Zhongzhi1228/Qwen3.5-122B-A10B-SFT.